© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    elements related to personal experience and recognition of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chauung
    -0.31
    значення
    -0.30
    reathe
    -0.29
    lında
    -0.27
    полне
    -0.27
     necesita
    -0.27
    angsaan
    -0.27
     Dänemark
    -0.27
    都需要
    -0.26
    lıkla
    -0.26
    POSITIVE LOGITS
     never
    3.64
    never
    3.13
    Never
    2.98
     Never
    2.97
     nunca
    2.81
     nigdy
    2.78
     NEVER
    2.59
     nikdy
    2.55
     nooit
    2.48
    NEVER
    2.47
    Activations Density 0.873%

    No Known Activations